ERGeoBench - Single-View GLS: leaderboard
Single-View geo-localization on ERGeoBench (2026): a model locates a real-world street scene from one fixed street-level view, scored by the Geo-localization Score, the mean of hierarchical street, city and country accuracy, distance-threshold hit rates and a log-scaled median error. Scale 0 to 100; higher is better.
Metric: Geo-localization Score, GLS (0-100): mean of the street, city and country accuracy, the hit rate within 1, 25, 200, 750 and 2,500 km, and a log-scaled median-error score, over the 2,207 street-level panoramas, located from one fixed 90-degree street-level view; unified structured prompt with egocentric observations, action history and in-context examples, temperature 0.1, first valid JSON object parsed (invalid outputs count as failures); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 9 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 65.93 | #276 |
| 2 | Gemini 3 Flash | 65.54 | #175 |
| 3 | Gemini 2.0 Flash | 64.5 | #723 |
| 4 | GPT-4o | 61.98 | #751 |
| 5 | InternVL3-8B | 39.24 | #1782 |
| 6 | Qwen 3 VL 8B | 38.59 | #917 |
| 7 | Qwen-VL-Max | 38.32 | #1400 |
| 8 | Qwen 2.5 VL 7B | 29.49 | #1862 |
| 9 | InternVL2.5-8B | 24.8 | #2370 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=ergeobench-single-view-gls · How It Works · Data refreshed daily, snapshot 2026-11-21.